shinys000114/linux
1
0
Fork 0
mirror of https://github.com/hardkernel/linux.git synced 2026-06-07 19:30:30 +09:00
Code Issues Packages Projects Releases Wiki Activity

arm64: Enable HMP for ARMv8

Browse Source 
Signed-off-by: Mark Hambleton <mahamble@broadcom.com>
Signed-off-by: Mark Brown <broonie@linaro.org>
This commit is contained in:
Mark Hambleton
2013-11-27 13:30:29 +00:00
committed by Mark Brown
parent d474d10a1a
commit 8ecd48091c
3 changed files with 246 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

96
arch/arm64/Kconfig
View File

@@ -168,6 +168,102 @@ config SCHED_SMT
MultiThreading at a cost of slightly increased overhead in some
places. If unsure say N here.
config DISABLE_CPU_SCHED_DOMAIN_BALANCE
bool "(EXPERIMENTAL) Disable CPU level scheduler load-balancing"
help
Disables scheduler load-balancing at CPU sched domain level.
config SCHED_HMP
bool "(EXPERIMENTAL) Heterogenous multiprocessor scheduling"
depends on DISABLE_CPU_SCHED_DOMAIN_BALANCE && SCHED_MC && FAIR_GROUP_SCHED && !SCHED_AUTOGROUP
help
Experimental scheduler optimizations for heterogeneous platforms.
Attempts to introspectively select task affinity to optimize power
and performance. Basic support for multiple (>2) cpu types is in place,
but it has only been tested with two types of cpus.
There is currently no support for migration of task groups, hence
!SCHED_AUTOGROUP. Furthermore, normal load-balancing must be disabled
between cpus of different type (DISABLE_CPU_SCHED_DOMAIN_BALANCE).
config SCHED_HMP_PRIO_FILTER
bool "(EXPERIMENTAL) Filter HMP migrations by task priority"
depends on SCHED_HMP
help
Enables task priority based HMP migration filter. Any task with
a NICE value above the threshold will always be on low-power cpus
with less compute capacity.
config SCHED_HMP_PRIO_FILTER_VAL
int "NICE priority threshold"
default 5
depends on SCHED_HMP_PRIO_FILTER
config HMP_FAST_CPU_MASK
string "HMP scheduler fast CPU mask"
depends on SCHED_HMP
help
Leave empty to use device tree information.
Specify the cpuids of the fast CPUs in the system as a list string,
e.g. cpuid 0+1 should be specified as 0-1.
config HMP_SLOW_CPU_MASK
string "HMP scheduler slow CPU mask"
depends on SCHED_HMP
help
Leave empty to use device tree information.
Specify the cpuids of the slow CPUs in the system as a list string,
e.g. cpuid 0+1 should be specified as 0-1.
config HMP_VARIABLE_SCALE
bool "Allows changing the load tracking scale through sysfs"
depends on SCHED_HMP
help
When turned on, this option exports the thresholds and load average
period value for the load tracking patches through sysfs.
The values can be modified to change the rate of load accumulation
and the thresholds used for HMP migration.
The load_avg_period_ms is the time in ms to reach a load average of
0.5 for an idle task of 0 load average ratio that start a busy loop.
The up_threshold and down_threshold is the value to go to a faster
CPU or to go back to a slower cpu.
The {up,down}_threshold are devided by 1024 before being compared
to the load average.
For examples, with load_avg_period_ms = 128 and up_threshold = 512,
a running task with a load of 0 will be migrated to a bigger CPU after
128ms, because after 128ms its load_avg_ratio is 0.5 and the real
up_threshold is 0.5.
This patch has the same behavior as changing the Y of the load
average computation to
(1002/1024)^(LOAD_AVG_PERIOD/load_avg_period_ms)
but it remove intermadiate overflows in computation.
config HMP_FREQUENCY_INVARIANT_SCALE
bool "(EXPERIMENTAL) Frequency-Invariant Tracked Load for HMP"
depends on HMP_VARIABLE_SCALE && CPU_FREQ
help
Scales the current load contribution in line with the frequency
of the CPU that the task was executed on.
In this version, we use a simple linear scale derived from the
maximum frequency reported by CPUFreq.
Restricting tracked load to be scaled by the CPU's frequency
represents the consumption of possible compute capacity
(rather than consumption of actual instantaneous capacity as
normal) and allows the HMP migration's simple threshold
migration strategy to interact more predictably with CPUFreq's
asynchronous compute capacity changes.
config SCHED_HMP_LITTLE_PACKING
bool "Small task packing for HMP"
depends on SCHED_HMP
default n
help
Allows the HMP Scheduler to pack small tasks into CPUs in the
smallest HMP domain.
Controlled by two sysfs files in sys/kernel/hmp.
packing_enable: 1 to enable, 0 to disable packing. Default 1.
packing_limit: runqueue load ratio where a RQ is considered
to be full. Default is NICE_0_LOAD * 9/8.
config NR_CPUS
int "Maximum number of CPUs (2-32)"
range 2 32

31
arch/arm64/include/asm/topology.h
View File

@@ -28,6 +28,37 @@ void store_cpu_topology(unsigned int cpuid);
const struct cpumask *cpu_coregroup_mask(int cpu);
int cluster_to_logical_mask(unsigned int socket_id, cpumask_t *cluster_mask);
#ifdef CONFIG_DISABLE_CPU_SCHED_DOMAIN_BALANCE
/* Common values for CPUs */
#ifndef SD_CPU_INIT
#define SD_CPU_INIT (struct sched_domain) { \
.min_interval = 1, \
.max_interval = 4, \
.busy_factor = 64, \
.imbalance_pct = 125, \
.cache_nice_tries = 1, \
.busy_idx = 2, \
.idle_idx = 1, \
.newidle_idx = 0, \
.wake_idx = 0, \
.forkexec_idx = 0, \
\
.flags = 0*SD_LOAD_BALANCE \
| 1*SD_BALANCE_NEWIDLE \
| 1*SD_BALANCE_EXEC \
| 1*SD_BALANCE_FORK \
| 0*SD_BALANCE_WAKE \
| 1*SD_WAKE_AFFINE \
| 0*SD_SHARE_CPUPOWER \
| 0*SD_SHARE_PKG_RESOURCES \
| 0*SD_SERIALIZE \
, \
.last_balance = jiffies, \
.balance_interval = 1, \
}
#endif
#endif /* CONFIG_DISABLE_CPU_SCHED_DOMAIN_BALANCE */
#else
static inline void init_cpu_topology(void) { }

119
arch/arm64/kernel/topology.c
View File

@@ -363,6 +363,125 @@ void store_cpu_topology(unsigned int cpuid)
update_cpu_power(cpuid);
}
#ifdef CONFIG_SCHED_HMP
/*
* Retrieve logical cpu index corresponding to a given MPIDR[23:0]
* - mpidr: MPIDR[23:0] to be used for the look-up
*
* Returns the cpu logical index or -EINVAL on look-up error
*/
static inline int get_logical_index(u32 mpidr)
{
int cpu;
for (cpu = 0; cpu < nr_cpu_ids; cpu++)
if (cpu_logical_map(cpu) == mpidr)
return cpu;
return -EINVAL;
}
static const char * const little_cores[] = {
"arm,cortex-a53",
NULL,
};
static bool is_little_cpu(struct device_node *cn)
{
const char * const *lc;
for (lc = little_cores; *lc; lc++)
if (of_device_is_compatible(cn, *lc))
return true;
return false;
}
void __init arch_get_fast_and_slow_cpus(struct cpumask *fast,
struct cpumask *slow)
{
struct device_node *cn = NULL;
int cpu;
cpumask_clear(fast);
cpumask_clear(slow);
/*
* Use the config options if they are given. This helps testing
* HMP scheduling on systems without a big.LITTLE architecture.
*/
if (strlen(CONFIG_HMP_FAST_CPU_MASK) && strlen(CONFIG_HMP_SLOW_CPU_MASK)) {
if (cpulist_parse(CONFIG_HMP_FAST_CPU_MASK, fast))
WARN(1, "Failed to parse HMP fast cpu mask!\n");
if (cpulist_parse(CONFIG_HMP_SLOW_CPU_MASK, slow))
WARN(1, "Failed to parse HMP slow cpu mask!\n");
return;
}
/*
* Else, parse device tree for little cores.
*/
while ((cn = of_find_node_by_type(cn, "cpu"))) {
const u32 *mpidr;
int len;
mpidr = of_get_property(cn, "reg", &len);
if (!mpidr || len != 8) {
pr_err("%s missing reg property\n", cn->full_name);
continue;
}
cpu = get_logical_index(be32_to_cpup(mpidr+1));
if (cpu == -EINVAL) {
pr_err("couldn't get logical index for mpidr %x\n",
be32_to_cpup(mpidr+1));
break;
}
if (is_little_cpu(cn))
cpumask_set_cpu(cpu, slow);
else
cpumask_set_cpu(cpu, fast);
}
if (!cpumask_empty(fast) && !cpumask_empty(slow))
return;
/*
* We didn't find both big and little cores so let's call all cores
* fast as this will keep the system running, with all cores being
* treated equal.
*/
cpumask_setall(fast);
cpumask_clear(slow);
}
struct cpumask hmp_slow_cpu_mask;
void __init arch_get_hmp_domains(struct list_head *hmp_domains_list)
{
struct cpumask hmp_fast_cpu_mask;
struct hmp_domain *domain;
arch_get_fast_and_slow_cpus(&hmp_fast_cpu_mask, &hmp_slow_cpu_mask);
/*
* Initialize hmp_domains
* Must be ordered with respect to compute capacity.
* Fastest domain at head of list.
*/
if(!cpumask_empty(&hmp_slow_cpu_mask)) {
domain = (struct hmp_domain *)
kmalloc(sizeof(struct hmp_domain), GFP_KERNEL);
cpumask_copy(&domain->possible_cpus, &hmp_slow_cpu_mask);
cpumask_and(&domain->cpus, cpu_online_mask, &domain->possible_cpus);
list_add(&domain->hmp_domains, hmp_domains_list);
}
domain = (struct hmp_domain *)
kmalloc(sizeof(struct hmp_domain), GFP_KERNEL);
cpumask_copy(&domain->possible_cpus, &hmp_fast_cpu_mask);
cpumask_and(&domain->cpus, cpu_online_mask, &domain->possible_cpus);
list_add(&domain->hmp_domains, hmp_domains_list);
}
#endif /* CONFIG_SCHED_HMP */
/*
* cluster_to_logical_mask - return cpu logical mask of CPUs in a cluster